Abstract
To address the challenge of uncertainty regarding
the attacker’s payoffs, capabilities and other characteristics, recent work in security games has focused on learning the optimal defense strategy from
observed attack data. This raises a natural concern
that the strategic attacker may mislead the defender
by deceptively reacting to the learning algorithms.
This paper focuses on understanding how such attacker deception affects the game equilibrium. We
examine a basic deception strategy termed imitative
deception, in which the attacker simply pretends
to have a different payoff assuming his true payoff is unknown to the defender. We provide a clean
characterization about the game equilibrium as well
as optimal algorithms to compute the equilibrium.
Our experiments illustrate significant defender loss
due to imitative attacker deception, suggesting the
potential side effect of learning from the attacker